Home >

news Help

Publication Information


Title
Japanese:被履ゲームに対する最適均衡解の探索：利得に基づく学習アルゴリズム設計 
English:Seeking Optimal Equiribria for Coveage Games: Payoff-based Leaning Approach 
Author
Japanese: 和佐泰明, 後藤達彦, 畑中健志, 藤田政之.  
English: Yasuaki Wasa, Tatsuhiko Gotou, Takeshi Hatanaka, Masayuki FUJITA.  
Language Japanese 
Journal/Book name
Japanese:システム制御情報学会論文誌 
English: 
Volume, Number, Page Vol. 25    No. 9    pp. 247-255
Published date 2012 
Publisher
Japanese: 
English: 
Conference name
Japanese: 
English: 
Conference site
Japanese: 
English: 
Abstract In this paper, we investigate game theoretic coverage control whose objective is to lead agents to optimal congurations over a mission space. In particular, the objective of this paper is to achieve the control objective (i) in the absense of the perfect prior knowledge on importance of each point and (ii) in the presence of the action constraints. For this purpose, we rst formulate coverage problems with two different global objective functions as so-called potential games. Then, we present a payoff-based learning algorithm determining actions based only on the past actual outcomes. The feature of the present algorithm is to allow an agent to take an irrational action. We also clarify a relation between a design parameter of the algorithm and the probability which agents take the optimal actions and prove that the probability can be arbitrarily increased. Then, we demonstrate the effectiveness of the present algorithm through experiments on a testbed.

©2007 Tokyo Institute of Technology All rights reserved.